replace file

[shahawi]

replace file no need to remove harakat

[shahawi]

The verses were copied from the same zip file containing the original csv file

[aelbuni]

Thanks Shahawi for your continuous contribution.

For the Harakaat, although it is really hard to use them for topic modeling, but for research purposes, we should keep them, as the same word with different harakat can give meanings that we want to retain through exclusion (Check this line)

Apart from that, it will be nice to convert this code into a packaged OOP library eventually, let me know if you are interested to restructure the code into a cleaner OOP format.

[shahawi]

Ok thanks understood,
Considering the OOP, I am an Android developer with very little experience in python and ML,
But I have free time and I love trying new things.
So if you can give me some pointers of what you want, I think I can help, after all java and python are both OOP.